Mistral Large 3 675B Instruct vs Mistral Small 4
Mistral Large 3 675B Instruct (2025) and Mistral Small 4 (2026) are compact production models from MistralAI. Mistral Large 3 675B Instruct ships a 128K-token context window, while Mistral Small 4 ships a 256K-token context window. On Google-Proof Q&A, Mistral Small 4 leads by 33.0 pts. On pricing, Mistral Small 4 costs $0.15/1M input tokens versus $0.5/1M for the alternative. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit.
Mistral Small 4 is ~233% cheaper at $0.15/1M; pay for Mistral Large 3 675B Instruct only for provider fit.
Decision scorecard
Local evidence first| Signal | Mistral Large 3 675B Instruct | Mistral Small 4 |
|---|---|---|
| Decision fit | Coding, RAG, and Agents | RAG, Agents, and Long context |
| Context window | 128K | 256K |
| Cheapest output | $1.5/1M tokens | $0.6/1M tokens |
| Provider routes | 4 tracked | 3 tracked |
| Shared benchmarks | 1 rows | Google-Proof Q&A leader |
Decision tradeoffs
- Mistral Large 3 675B Instruct has broader tracked provider coverage for fallback and procurement flexibility.
- Mistral Large 3 675B Instruct uniquely exposes Structured outputs in local model data.
- Local decision data tags Mistral Large 3 675B Instruct for Coding, RAG, and Agents.
- Mistral Small 4 leads the largest shared benchmark signal on Google-Proof Q&A by 33.0 points.
- Mistral Small 4 has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Mistral Small 4 has the lower cheapest tracked output price at $0.6/1M tokens.
- Mistral Small 4 uniquely exposes Vision, Multimodal, and Function calling in local model data.
- Local decision data tags Mistral Small 4 for RAG, Agents, and Long context.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output prices on this page.
Mistral Large 3 675B Instruct
$775
Cheapest tracked route: AWS Bedrock
Mistral Small 4
$270
Cheapest tracked route: OpenRouter
Estimated monthly gap: $505. Batch, cache, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on NVIDIA NIM and Mistral AI Studio; start route-level A/B tests there.
- Mistral Small 4 is $0.9/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Structured outputs before moving production traffic.
- Mistral Small 4 adds Vision, Multimodal, and Function calling in local capability data.
- Provider overlap exists on NVIDIA NIM and Mistral AI Studio; start route-level A/B tests there.
- Mistral Large 3 675B Instruct is $0.9/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Check replacement coverage for Vision, Multimodal, and Function calling before moving production traffic.
- Mistral Large 3 675B Instruct adds Structured outputs in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2025-12-01 | 2026-03-16 |
| Context window | 128K | 256K |
| Parameters | 675B | 119B (6.5B active) |
| Architecture | decoder only | moe |
| License | 1 | Apache 2.0 |
| Knowledge cutoff | 2024-11 | 2025-06 |
Pricing and availability
| Pricing attribute | Mistral Large 3 675B Instruct | Mistral Small 4 |
|---|---|---|
| Input price | $0.5/1M tokens | $0.15/1M tokens |
| Output price | $1.5/1M tokens | $0.6/1M tokens |
| Providers |
Capabilities
| Capability | Mistral Large 3 675B Instruct | Mistral Small 4 |
|---|---|---|
| Vision | No | Yes |
| Multimodal | No | Yes |
| Reasoning | No | No |
| Function calling | No | Yes |
| Tool use | No | Yes |
| Structured outputs | Yes | No |
| Code execution | No | No |
Benchmarks
| Benchmark | Mistral Large 3 675B Instruct | Mistral Small 4 |
|---|---|---|
| Google-Proof Q&A | 43.9 | 76.9 |
Deep dive
On shared benchmark coverage, Google-Proof Q&A has Mistral Large 3 675B Instruct at 43.9 and Mistral Small 4 at 76.9, with Mistral Small 4 ahead by 33.0 points. The largest visible gap is 33.0 points on Google-Proof Q&A, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.
The capability footprint differs most on vision: Mistral Small 4, multimodal input: Mistral Small 4, function calling: Mistral Small 4, tool use: Mistral Small 4, and structured outputs: Mistral Large 3 675B Instruct. Both models share the core language-model surface, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.
For cost, Mistral Large 3 675B Instruct lists $0.5/1M input and $1.5/1M output tokens, while Mistral Small 4 lists $0.15/1M input and $0.6/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Mistral Small 4 lower by about $0.51 per million blended tokens. Availability is 4 providers versus 3, so concentration risk also matters.
Choose Mistral Large 3 675B Instruct when provider fit and broader provider choice are central to the workload. Choose Mistral Small 4 when long-context analysis, larger context windows, and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which has a larger context window, Mistral Large 3 675B Instruct or Mistral Small 4?
Mistral Small 4 supports 256K tokens, while Mistral Large 3 675B Instruct supports 128K tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Which is cheaper, Mistral Large 3 675B Instruct or Mistral Small 4?
Mistral Small 4 is cheaper on tracked token pricing. Mistral Large 3 675B Instruct costs $0.5/1M input and $1.5/1M output tokens. Mistral Small 4 costs $0.15/1M input and $0.6/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Mistral Large 3 675B Instruct or Mistral Small 4 open source?
Mistral Large 3 675B Instruct is listed under 1. Mistral Small 4 is listed under Apache 2.0. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for vision, Mistral Large 3 675B Instruct or Mistral Small 4?
Mistral Small 4 has the clearer documented vision signal in this comparison. If vision is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for multimodal input, Mistral Large 3 675B Instruct or Mistral Small 4?
Mistral Small 4 has the clearer documented multimodal input signal in this comparison. If multimodal input is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Where can I run Mistral Large 3 675B Instruct and Mistral Small 4?
Mistral Large 3 675B Instruct is available on AWS Bedrock, NVIDIA NIM, Mistral AI Studio, and Microsoft Foundry. Mistral Small 4 is available on OpenRouter, NVIDIA NIM, and Mistral AI Studio. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-05-19. Data sourced from public model cards and provider documentation.